{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "datalab-to/indra",
 "name": "indra",
 "owner": "datalab-to",
 "slug": "datalab-to-indra",
 "github": "https://github.com/datalab-to/indra",
 "what": "Indra OCR is a CPU-based OCR tool that turns PDFs and images into markdown, text, or JSON with boxes, layout blocks, and reading order.",
 "why": "",
 "language": "Python",
 "requirements": [
  "Python 3.10 or newer (the README says it is tested on Linux and macOS)",
  "pip to install the indra-ocr package",
  "An internet connection for the first run, which downloads about 76 MB of models from Hugging Face",
  "The PDFs or images to read"
 ],
 "audience_note": "People with scanned PDFs or photographed pages who need searchable text on a laptop or CPU-only server, and developers who want OCR output with boxes and layout labels in their own pipelines.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/datalab-to-indra/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "datalab-to-indra--scanned-pdfs-to-searchable-markdown",
   "title": "Turn a folder of scanned PDFs into markdown files",
   "best": true,
   "url": "https://dedupedai.com/use-cases/datalab-to-indra/scanned-pdfs-to-searchable-markdown/",
   "json": "https://dedupedai.com/use-cases/u/datalab-to-indra/scanned-pdfs-to-searchable-markdown.json"
  },
  {
   "id": "datalab-to-indra--ocr-to-json-with-boxes-for-a-pipeline",
   "title": "Get OCR lines and boxes as JSON for a data pipeline",
   "best": false,
   "url": "https://dedupedai.com/use-cases/datalab-to-indra/ocr-to-json-with-boxes-for-a-pipeline/",
   "json": "https://dedupedai.com/use-cases/u/datalab-to-indra/ocr-to-json-with-boxes-for-a-pipeline.json"
  },
  {
   "id": "datalab-to-indra--review-ocr-output-in-local-viewer",
   "title": "Check OCR results on each page in a local viewer",
   "best": false,
   "url": "https://dedupedai.com/use-cases/datalab-to-indra/review-ocr-output-in-local-viewer/",
   "json": "https://dedupedai.com/use-cases/u/datalab-to-indra/review-ocr-output-in-local-viewer.json"
  },
  {
   "id": "datalab-to-indra--ocr-multilingual-and-handwritten-scans",
   "title": "Read mixed-language and handwritten scans in one run",
   "best": false,
   "url": "https://dedupedai.com/use-cases/datalab-to-indra/ocr-multilingual-and-handwritten-scans/",
   "json": "https://dedupedai.com/use-cases/u/datalab-to-indra/ocr-multilingual-and-handwritten-scans.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}